JP7080608B2 - Recommendation device, recommendation method and recommendation program - Google Patents

Description

The present invention relates to a recommendation device, a recommendation method and a recommendation program.

Today, there is known a service that recommends a related product related to a purchased product to a user based on the purchase history of the product purchased via a network or the like.

For example, Patent Document 1 (Japanese Unexamined Patent Publication No. 2016-206794) discloses an information processing device that recommends a transaction target based on information obtained from the transaction history of the user himself / herself. In the case of this information processing device, the information of the history in which the user has purchased or browsed the product is divided into each item included in the hierarchy based on the hierarchical information in which the product is divided into items in a plurality of layers. Then, the purchasing tendency is modeled based on the entropy calculated for each layer from the history information divided for each item, and the product corresponding to the modeled result is recommended to the user.

Further, Patent Document 2 (Japanese Unexamined Patent Publication No. 2016-181196) discloses an information processing device that recommends a product that matches a user's taste based on product information including the content of a product image or a product description. There is. In the case of this information processing device, the product data including the product image and the product description is converted into the feature amount, machine learning is performed together with the feature amount of the user data for purchasing the product, and the feature amount of the user data and the feature amount of the product data are used. Create a correlation learning model that learns the correlation with. In addition, the feature amount of the user data corresponding to the user who accessed the site for purchasing the product and the feature amount of the product data are acquired, and machine learning to which the correlation learning model is applied is executed to calculate the goodness of fit. Then, the recommendation order is determined based on the calculated goodness of fit, and each determined product is recommended to the user.

Japanese Unexamined Patent Publication No. 2016-206794 Japanese Unexamined Patent Publication No. 2016-181196

However, there is a timing suitable for recommendation, such as when the demand for a product increases. Therefore, it is preferable to recommend products at a timing suitable for each product.

The present application has been made in view of the above, and an object of the present application is to provide a recommendation device, a recommendation method, and a recommendation program for making recommendations for purchasing products at appropriate timings for each product.

The recommendation device according to the present application is a specific unit that identifies a product whose sales increase within a predetermined period based on sales information indicating a sales transition of the product, and a predetermined unit from a time when the sales of the product specified by the specific unit increase. It has a notification unit that gives notifications about products before the period.

According to one aspect of the embodiment, there is an effect that a recommendation for purchasing a product or the like can be made at a timing suitable for each product.

FIG. 1 is a diagram for explaining an outline of the recommendation process performed in the first embodiment and the second embodiment. FIG. 2 is a system configuration diagram of a recommender system according to the first embodiment. FIG. 3 is a block diagram of a main part of the recommendation device of the recommendation system of the first embodiment. FIG. 4 is a diagram showing an example of sales information stored in the recommendation device of the recommendation system of the first embodiment. FIG. 5 is a diagram showing an example of user information stored in the recommendation device of the recommendation system of the first embodiment. FIG. 6 is a flowchart for explaining a product recommendation operation in the recommendation device of the recommendation system of the first embodiment. FIG. 7 is a diagram for explaining the transition of the number of sales of the product every month. FIG. 8 is a block diagram of a main part of the recommendation device of the recommendation system of the second embodiment. FIG. 9 is a diagram showing an example of purchase history information stored in the recommendation device of the recommendation system of the second embodiment. FIG. 10 is a diagram showing an example of search information stored in the recommendation device of the recommendation system of the second embodiment. FIG. 11 is a flowchart for explaining a product recommendation operation in the recommendation device of the recommendation system of the second embodiment. FIG. 12 is a hardware configuration diagram of a recommendation device provided in the recommendation system of the first embodiment and the second embodiment.

Hereinafter, as an example, a recommender system to which a recommendation device, a recommendation method, and a recommendation program according to the present application is applied is a mode for implementing the recommendation device, the recommendation method, and the recommendation program according to the present application (hereinafter, referred to as “embodiment”). Will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the recommendation device, the recommendation method, and the recommendation program according to the present application. In addition, each embodiment can be appropriately combined as long as the processing contents do not contradict each other. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate explanations are omitted.

[Example of recommendation processing]
First, an example of the recommendation process according to the first embodiment and the second embodiment will be described with reference to FIG. In the recommendation process of the first embodiment, the recommendation device 1 detects a product whose sales increase within a predetermined period from the present time. The term "commodity" is a concept that includes intangible services such as services provided to people, etc., in addition to tangible goods.

The example shown in FIG. 1 shows the transition of sales of school bags, socks and athletic shoes. In the case of this example, school bags show an increase in sales in December, socks have a roughly uniform sales year-round, and athletic shoes have an increase in sales in April and September. The recommendation device 1 detects such a transition in sales of each product.

Further, when the current date (current time) is October 1, the recommendation device 1 detects the presence or absence of a product whose sales increase within a predetermined period such as within two months from this October 1. In the case of the example shown in FIG. 1, the product whose sales increase within two months from the current October 1st is a school bag. For this reason, the recommendation device 1 notifies the user by notifying the user that the product is expected to be sold out, for example, one month or two months before the time when the sales increase due to the increase in demand. I recommend you to buy the product.

As a result, it is possible to recommend the user to purchase the product at a timing suitable for each product. In addition, users can be encouraged to purchase products that are likely to be needed in the future, before the products are sold out due to the increase in sales over time and it becomes difficult to purchase the products.

The above is the outline of the recommendation process of the first embodiment. In addition, in the recommendation process of the second embodiment, the recommendation device 1 refers to the user specified based on the user's purchase history, search information, and the like. Therefore, it is recommended to purchase the product at the above-mentioned timing suitable for each product. In addition, instead of simply identifying the user based on the purchase history, for example, we recommend that users who purchased baby products 6 years ago purchase school bags for elementary school students when 6 years have passed. As described above, the product that the user needs is estimated with the passage of time, and the user is recommended to purchase the product at an appropriate timing for each of the above-mentioned products. As a result, it is possible to recommend the purchase of the product that is really needed to the user who really needs it.

Hereinafter, the configuration and the like of the recommendation device 1 including the recommendation device 1 and the recommendation device 1 that perform such a recommendation process will be described in detail for each embodiment.
[First Embodiment]
(System configuration)
FIG. 2 shows a system configuration diagram of a recommender system according to the first embodiment. As shown in FIG. 1, the recommender system has one or more recommendation devices 1 and one or more user terminals 2. The recommendation device 1 and the user terminal 2 are connected to each other via a predetermined network 3 such as the Internet or a LAN (Local Area Network).

As the user terminal 2, in addition to a desktop type and a notebook type personal computer device, a mobile phone, a smartphone terminal, a tablet type terminal, and the like, as well as a wearable terminal such as a glasses type or a clock type can be used.

(Configuration of Recommended Device of First Embodiment)
The control unit 6 is a controller, and is realized by, for example, executing a recommendation program 22 with a RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Further, the control unit 6 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 6 shown in FIG. 3 controls communication with the user terminal 2 and executes the recommendation program 22 to realize the specific unit 31 and the notification unit 32. As will be described later, the control unit 6 functions as the specific unit 31 to detect a product whose sales increase within a predetermined period. Further, the control unit 6 functions as a notification unit 32 to notify the user of the existence of a product whose sales increase within a predetermined period and recommend the purchase.

Further, the recommendation program 22 that realizes each function is provided by recording a file in an installable format or an executable format on a recording medium that can be read by a computer device such as a CD-ROM or a flexible disk (FD). May be good. Further, the recommendation program 22 may be provided by recording on a recording medium readable by a computer device such as a CD-R, a DVD (Digital Versatile Disk), a Blu-ray disc (registered trademark), or a semiconductor memory. Further, the recommendation program 22 may be provided in the form of being installed via a network such as the Internet. Further, the recommendation program 22 may be provided by incorporating it into a ROM or the like in the mobile terminal in advance.

(Sales information format)
FIG. 4 is an example of the format of the sales information 23 stored in the storage unit 7. The sales information 23 and the user information 24 described later are aggregated and distributed by, for example, a shopping server device on the network 3. The recommendation device 1 acquires sales information 23 and user information 24 from the shopping server device and stores them in the storage unit 7. In this example, the sales information 23 and the user information 24 are acquired from the shopping server device, but the sales information and the user information may be acquired from the computer device of the actual store or the like.

As illustrated in FIG. 4, the user identification number (user ID), sales date, product name, number of units sold, store name, product price, etc. of the user who purchased the product are obtained from the shopping server device as sales information 23. It will be delivered. The control unit 6 of the recommendation device 1 stores and controls the sales information 23 acquired from the shopping server device in the storage unit 7.

The example shown in FIG. 4 shows sales information 23 when a user with a user ID of "A123" purchases five pairs of baby socks from an AB clothing store for 1,500 yen on August 10, 2011. In this case, the user ID of "A123", the sales date of "August 10, 2011", the product name of "socks (for infants)", the number of sales of "5 pairs", and the sales of "AB clothing store". Information indicating the store name and the price of the product of "1500 yen" is distributed from the shopping server device as sales information 23. Similarly, the example shown in FIG. 4 shows sales information 23 when a user with a user ID of "B911" purchases one school bag from an F department store web store for 51,000 yen on December 1, 2011. .. In this case, the user ID of "B911", the sales date of "December 1, 2011", the product name of "Randsel", the number of units sold of "1", the sales store name of "F department store web store", and , Information indicating the price of the product of "5100 yen" is delivered from the shopping server device as sales information 23. The control unit 6 stores and controls such sales information 23 in the storage unit 7.

(User information format)
FIG. 5 is an example of the format of the user information 24 stored in the storage unit 7. As illustrated in FIG. 5, the control unit of the recommendation device 1 in which the user ID, user name, e-mail address (mobile phone address), address, telephone number, and the like are delivered as user information 24 from the shopping server device. 6 stores the user information 24 acquired from the shopping server device in the storage unit 7. Examples of FIG. 5 include a user ID of "A123", a user name of "○○○○", an e-mail address of "A@B.com", an address of "○○, Sapporo City, Hokkaido", and "011- ○". An example is shown in which the telephone number or the like of "○○○-××××" is delivered from the shopping server device as the user information 24. Similarly, in the example of FIG. 5, the user ID of "A127", the user name of "○○ XX", the e-mail address of "C@D.co.jp", and the address of "Yokohama City, Kanagawa Prefecture XX" , "090- ○○○○-××××" is shown as an example of being delivered from the shopping server device as user information 24. The control unit 6 stores and controls such user information 24 in the storage unit 7.

(Product recommendation operation of the first embodiment)
Next, the product recommendation operation in the recommendation system of the first embodiment will be described. FIG. 6 is a flowchart showing a flow of product recommendation operation in the recommendation system of the first embodiment. This flowchart is executed by the control unit 6 shown in FIG. 3 based on the recommendation program 22 stored in the storage unit 7 at predetermined time intervals, for example, every 3 hours, every day, or every month. .. In this example, the processing of the flowchart of FIG. 6 is executed at predetermined time intervals, but it may be executed at any timing such as a timing specified by an administrator or the like.

In step S1, the specifying unit 31 identifies a product whose sales number increases within a predetermined period based on the sales information 23 shown in FIG. For example, FIG. 7 shows changes in the number of school bags sold. School bags require new students to become elementary school students from April of the following year, and because they are expensive, sales tend to increase in December of the previous year, which is the bonus period. Then, if the sales of this school bag are expected to increase within a predetermined period from the current date and time, it is expected that the school bag will be sold out. Identify.

In this example, whether or not the sales increase is specified on a monthly basis, but if the sales fluctuate on an hourly basis in a day, the presence or absence of an increase in sales may be specified on an hourly basis. If the sales fluctuate on a daily basis in January, it may be specified whether or not the sales increase on a daily basis.

Next, in step S2 of the flowchart of FIG. 6, the specific unit 31 determines whether or not there is a product (recommended product) whose sales increase within a predetermined period. For example, in the case of the school bag described with reference to FIG. 7, December is the time for increasing sales. Therefore, the specific unit 31 determines whether or not the current date is within a predetermined period such as two months from the beginning of December (December 1) when the sales of the school bag increase. do.

Also, for example, if "October 1" is the current date (current time), this current date will be the date within 2 months (within the specified period) from the beginning of December when the sales of school bags increase. (Step S2: Yes). In this case, the process proceeds to step S3, and the notification unit 32 shown in FIG. 3 notifies each user that the time for increasing the sales of the school bag is near, based on the user information 24 described with reference to FIG. Notify that the month that may be sold out is approaching).

In addition, the notification unit 32 gives the above-mentioned notification including information indicating when the recommended product is needed. Specifically, in the case of a school bag, it will be required at the time of admission in April of the following year. Therefore, the notification unit 32 gives the above-mentioned notification including information indicating when the recommended product is required, such as "A school bag will be required for admission in April next year". As a result, it is possible to inform each user that the recommended product is a product with high necessity, and it is possible to further increase the possibility that the user purchases the recommended product.

In step S3, the notification unit 32 says, for example, "If you have a child who goes on to elementary school, you will need a school bag in April next year. The school bag is expected to be sold out at the peak of sales in December every year. The communication unit 15 is to create an e-mail that announces the sold out of the product, etc., such as "We recommend you to purchase as soon as possible" and send it to each user based on the above user information 24. Communication control. As a result, each user in which the user information 24 is registered can consider purchasing a product that is likely to be needed in the future before the product is sold out.

In this example, the user is notified by e-mail, but each user may be notified by displaying the above-mentioned text or the like as an advertisement on the portal site, or each user may be notified. You may give a push notification to it.

Further, in step S2 described above, if it is determined by the specific unit 31 that there is no product whose sales increase within a predetermined period such as two months (step S2: No), the above-mentioned user is notified. Since it is not the timing to perform the process, the process of the flowchart of FIG. 6 ends as it is.

(Effect of the first embodiment)
As is clear from the above description, the recommender system of the first embodiment detects a product at a time when sales increase within a predetermined period and notifies each user. This makes it possible to encourage each user to consider purchasing a product and recommend the purchase of a product that meets the potential needs of the user before the sales increase and the product is sold out. In addition, it is possible to make recommendations for purchasing products at appropriate timings for each product.

In addition, the recommender system of the first embodiment can sell more than a normal number of products even before the peak sales period is reached. In addition, as an example, even a seller who manages products by the minimax method, which places an order for products so as to maximize the inventory of products when the inventory of products is minimized, has a surplus. It is possible to prevent the generation of inventory as much as possible and improve the sales of products.

[Second Embodiment]
Next, the recommendation system of the second embodiment will be described. The example of the first embodiment described above was an example of notifying each user of a product at which sales are expected to increase. On the other hand, the recommender system of the second embodiment described below is an example of identifying a user who is likely to be needed in the future and recommending the product among the users who recommend the product. It should be noted that the first embodiment described above and the second embodiment described below differ only in this respect. Therefore, in the following, only the difference between the two will be explained, and the duplicate explanation will be omitted.

(Configuration of Recommended Device of Second Embodiment)
FIG. 8 is a block diagram of a main part of the recommendation device 1 in the recommendation system of the second embodiment. As shown in FIG. 8, in the case of the second embodiment, the recommendation device 1 has a communication unit 5, a control unit 6, and a storage unit 7 as in the first embodiment described above. In addition to the above-mentioned operation system (OS) 21, sales information 23, and user information 24, the storage unit 7 contains a recommendation program 51 for the recommendation device 1 of the second embodiment, purchase history information 52, and search information 53 (log). An example of information) is stored.

The control unit 6 realizes the estimation unit 41 and the detection unit 42 in addition to the specific unit 31 and the notification unit 32 by executing the recommendation program 51. As will be described later, the control unit 6 functions as the specific unit 31 to detect a product whose sales increase within a predetermined period. Further, the control unit 6 functions as a detection unit 42 to detect a user who has purchased a product (recommended product) whose sales increase within a predetermined period. Further, the control unit 6 functions as the estimation unit 41. A user with a search history that is the same as or similar to the search history of the user who purchased the recommended product is estimated as a user who is likely to purchase the recommended product. Then, the control unit 6 functions as the notification unit 32 to notify the user who has detected the existence of the recommended product based on the above-mentioned search history and recommend the purchase.

(Purchase history information format)
FIG. 9 is an example of the format of the purchase history information 52 stored in the storage unit 7. The purchase history information 52 and the search information 53 described later are aggregated and distributed by the shopping server device on the network 3 together with the sales information 23 and the user information 24 described above. The recommendation device 1 acquires the purchase history information 52 and the search information 53 together with the sales information 23 and the user information 24 from the shopping server device, and stores them in the storage unit 7. In this example, the purchase history information 52 and the search information 53 are acquired from the shopping server device, but the purchase history information 52 and the search information 53 may be acquired from the computer device or the like of the actual store. , Same as above.

As illustrated in FIG. 9, as the purchase history information 52, a user ID, a user name, a purchase date, a product name, a number of purchases, a purchase store name, a purchase amount, and the like are delivered from the shopping server device. The example shown in FIG. 9 shows that a user with a user ID of A123 purchased five pairs of baby socks from an AB clothing store on August 10, 2011, and the purchase price was 1500 yen. An example in which the history information 52 is delivered is shown. Similarly, in the example shown in FIG. 9, a user with a user ID of B911 purchased a pair of athletic shoes from a J shoe store on September 4, 2016, and the purchase price was 3500 yen. An example in which the history information 52 is delivered is shown. The control unit 6 stores and controls such purchase history information 52 in the storage unit 7.

(Search information format)
FIG. 10 is an example of the format of the search information 53 stored in the storage unit 7. As illustrated in FIG. 10, as the search information 53, a user ID, a user name, a search time (search date, day, hour, minute, second), a search word, and the like are delivered from the shopping server device. The example shown in FIG. 10 shows that the user with the user ID A123 performed a network search using the search word (query) of "shoe, baby, cotton" on August 10, 2011. 53 indicates that it has been delivered. Similarly, in the example shown in FIG. 10, the search information 53 indicating that the user with the user ID B911 performed a network search using the search word "carrying string, price" on June 10, 2011, Indicates that it was delivered.

Hereinafter, an example of detecting another user who is performing the same or similar network search as the user who purchased the recommended product will be described using the search word (query) input by the user (purchaser). However, instead of or together with the search word, browsing history information that is information about the content viewed by the purchaser and / or purchase history information that is information about the product purchased by the purchaser is used. You may.

(Product recommendation operation of the second embodiment)
Next, the product recommendation operation in the recommendation system of the second embodiment will be described. FIG. 11 is a flowchart showing a flow of product recommendation operation in the recommendation system of the second embodiment. Each process of step S1 and step S2 of this flowchart is the same process as each process of step S1 and step S2 of the flowchart of FIG. That is, in step S1 and step S2, the specifying unit 31 specifies a recommended product whose sales increase within a predetermined period. As a result, the process proceeds to step S11. For the detailed operations of steps S1 and S2, refer to the above description of the first embodiment.

Next, in step S11, the detection unit 42 shown in FIG. 8 purchases the recommended product (the product specified in step S2) in the past by referring to the purchase history information 52 of each user described with reference to FIG. Detects the user who did. Specifically, when, for example, a "school bag" is specified as a recommended product by the specific unit 31, the detection unit 42 detects a user who has purchased the school bag by referring to the purchase history information 52. In the case of the example shown in FIG. 9, a user with a user ID of A123 purchased a school bag on December 1, 2017. Therefore, the detection unit 42 detects a user whose user ID is A123 as a user who has purchased a recommended product in the past.

Next, in step S12, the estimation unit 41 detects a user having the same or similar log information based on the log information of the user detected in step S11. Specifically, in the example of the purchase history information 52 shown in FIG. 9, the user whose user ID is A123 purchased the school bag on December 1, 2017. Looking at the search information 53 of the user whose user ID is A123 with reference to the search information 53 shown in FIG. 10, from August 10, 2011, which is six years before December 1, 2017, when the land cell was purchased. During September 3, 2011, we searched for search words such as "socks," "for babies," and "carrying strings." This is because a newborn baby will be born in 2011 for a user (or relatives, etc.) with a user ID of A123, and six years later, on December 1, 2017, preparations for the entrance ceremony of the elementary school to be held in April 2018 will be held. It means that you are doing.

Therefore, in step S12, the estimation unit 41 searches six years ago with search words for newborn babies such as "socks", "for infants", and "carrying straps" as in the case of users with user ID A123. Other users are detected from the search information 53. In the case of the example of FIG. 10, the user whose user ID is B911 searches with the search words "carrying string" and "price" at about the same time as the user whose user ID is A123, which is 6 years ago. There is. Therefore, it is highly possible that a user (or relative, etc.) with a user ID of B911 will have a newborn baby in 2011 and is preparing for the entrance ceremony of the elementary school to be held in April 2018. Therefore, the estimation unit 41 detects the user whose user ID is B911 as the user whose log information is the same as or similar to the user who purchased the recommended product (the user whose user ID is A123).

By detecting other users who are searching with the same search information 53 as the search information 53 of the user who purchased the recommended product, other users in the same living environment as the user who purchased the recommended product can be detected. Can be detected. That is, it is possible to identify and detect (estimate) a user who is likely to need the recommended product in the future and who is likely to purchase the recommended product.

When another user in a living environment similar to the living environment of the user who purchased the recommended product is detected, the notification unit 32 searches in step S13 in the same manner as the search information 53 of the user who purchased the recommended product. As described above, notification control such as e-mail is performed for other users who are searching with information 53. As a result, it is possible to identify users who are more likely to purchase and users who will need to purchase in the future, and notify them to recommend the purchase of the product.

(Effect of the second embodiment)
As is clear from the above description, the recommendation system of the second embodiment can obtain the same effect as the recommendation system of the first embodiment described above, and can also obtain the following effects.

Similar to the search information 53 of the user who purchased the recommended product In order to recommend the purchase of the recommended product to other users who are searching with the same search information 53, in the same living environment as the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to be living. Therefore, it is possible to recommend the purchase of the product by specifying the user who is more likely to purchase the product and the user who will need to purchase the product in the future.

[Hardware configuration]
The recommendation device 1 and the user terminal 2 of each of the above-described embodiments are realized by, for example, a computer device having the configuration shown in FIG. Hereinafter, the recommended device 1 will be described as an example. FIG. 12 is a hardware configuration diagram showing an example of a computer device that realizes the function of the recommended device 1. This computer device has a CPU 11, a RAM 12, a ROM 13, an HDD 14, a communication unit 15, an input / output interface (I / F) 16, and a media interface (I / F) 17.

The CPU 11 corresponds to the control unit 6 shown in FIGS. 3 and 8. The CPU 11 operates based on the program stored in the ROM 13 or the HDD 14, and controls each part. The ROM 13 stores a boot program executed by the CPU 11 when the computer device is started, a program depending on the hardware of the computer device, and the like.

The RAM 12 to the HDD 14 correspond to the storage unit 7 shown in FIGS. 3 and 8. The HDD 14 stores programs executed by the CPU 11 and data used in these programs. The communication unit 15 corresponds to the communication unit 5 shown in FIGS. 3 and 8. The communication unit 15 receives data from another device via the network 3 shown in FIG. 2, transfers the data to the CPU 11, and transmits the data generated by the CPU 11 to the other device via the network 3.

The CPU 11 controls an output device such as a display device and a printer device, and an input device such as a keyboard device and a mouse device via the input / output interface 16. The CPU 11 acquires data from the input device via the input / output interface 16. Further, the CPU 11 outputs the data generated via the input / output interface 16 to the output device.

The media interface 17 reads the program or data stored in the recording medium 18 and provides the program or data to the CPU 11 via the RAM 12. The CPU 11 loads the program from the recording medium 18 onto the RAM 12 via the media interface 17, and executes the loaded program. The recording medium 18 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer device operates as the recommendation device 1 according to the embodiment, the CPU 11 of the computer device realizes the function of the control unit 6 by executing the above-mentioned recommendation program loaded on the RAM 12. Further, the data in the storage unit 7 is stored in the HDD 14. The CPU 11 of the computer device reads these programs from the recording medium 18 and executes them, but as another example, these programs may be acquired from another device via the network 3.

〔others〕
Of the processes described in each of the above embodiments, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually. All or part of it can be done automatically by a known method. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown in the figure.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured. Further, each of the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

〔effect〕
As described above, the recommender device 1 of the recommender system of each embodiment has a specific unit 31 for specifying a product whose sales increase within a predetermined period based on sales information indicating a sales transition of the product, and a specific unit 31. It has a notification unit 32 for notifying the product about a predetermined period from the time when the sales of the product specified by the product increase.

This makes it possible to encourage each user to consider purchasing a product and recommend the purchase of a product that meets the potential needs of the user before the sales increase and the product is sold out. In addition, it is possible to make recommendations for purchasing products at appropriate timings for each product.

In addition, at least sales information including information indicating the date on which the product was sold and information indicating the number of units sold is used. As a result, it is possible to more clearly identify the products whose sales increase within a predetermined period.

Further, it further has an estimation unit 41 that estimates a user who is expected to purchase the product based on the purchaser information about the purchaser of the product, and the notification unit 32 tells the user estimated by the estimation unit 41 the product. Notify about.

As a result, the purchase of the recommended product is recommended to other users who are searching with the same search information 53 as the search information 53 of the user who purchased the recommended product, so that the same as the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to live in a living environment. Therefore, it is possible to recommend the purchase of the product by specifying the user who is more likely to purchase the product and the user who will need to purchase the product in the future.

Further, the estimation unit 41 sets the user who has the same or similar living environment as the purchaser's living environment based on the purchaser information including the information on the purchaser's living environment at the time when the purchaser purchases the product. Estimate as a user who is expected to purchase.

As a result, it is possible to identify users who are more likely to purchase and users who will need to purchase in the future, and recommend the purchase of the product.

Further, the estimation unit 41 is at least one of a search query entered by the purchaser, a browsing history which is information about the content browsed by the purchaser, and a purchase history which is information about the product purchased by the purchaser. Based on this, we estimate information about the living environment of the purchaser.

As a result, it is possible to identify users who are more likely to purchase and users who will need to purchase in the future, and recommend the purchase of the product.

In addition, the specific unit 31 identifies a product that is expected to be sold out in the future as a product whose sales increase within a predetermined period.

As a result, it is possible to promote the purchase of products that are more necessary to the user.

In addition, the notification unit 32 gives a notification including information indicating when the product specified by the specific unit 31 is needed.

This makes it possible to clearly indicate to the user when the product is needed.

Further, in the recommendation method applied to the recommendation device 1 of the recommendation system of each embodiment, the specific unit 31 identifies a product whose sales increase within a predetermined period based on the sales information indicating the sales transition of the product. The specific step and the notification unit 32 give a notification regarding the product before a predetermined period from the time when the sales of the product specified by the specific unit 31 increase.

This makes it possible to encourage each user to consider purchasing a product and recommend the purchase of a product that meets the potential needs of the user before the sales increase and the product is sold out. In addition, it is possible to make recommendations for purchasing products at appropriate timings for each product.

Further, in the recommendation method applied to the recommendation device 1 of the recommendation system of each embodiment, the estimation unit 41 estimates the user who is expected to purchase the product based on the purchaser information regarding the purchaser of the product. In the notification step, the notification unit 32 notifies the user estimated by the estimation unit 41 about the product.

As a result, the purchase of the recommended product is recommended to other users who are searching with the same search information as the user who purchased the recommended product, so that the living environment is the same as that of the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to live in Japan. Therefore, it is possible to recommend the purchase of the product by specifying the user who is more likely to purchase the product and the user who will need to purchase the product in the future.

Further, the recommendation program executed by the recommendation device 1 of the recommendation system of each embodiment is a specific unit that identifies a product whose sales increase within a predetermined period based on the sales information 23 indicating the sales transition of the product. It functions as a notification unit 32 for notifying the product 31 and a predetermined period before the time when the sales of the product specified by the specific unit 31 increase.

This makes it possible to encourage each user to consider purchasing a product and recommend the purchase of a product that meets the potential needs of the user before the sales increase and the product is sold out. In addition, it is possible to make recommendations for purchasing products at appropriate timings for each product.

Further, in the recommendation program executed by the recommendation device 1 of the recommendation system of each embodiment, the computer is used as an estimation unit 41 for estimating a user who is expected to purchase the product based on the purchaser information about the purchaser of the product. Further functioning, the notification unit notifies the user estimated by the estimation unit 41 about the product.

As a result, the purchase of the recommended product is recommended to other users who are searching with the same search information 23 as the search information 23 of the user who purchased the recommended product, so that the same as the user who purchased the recommended product. It is possible to recommend the purchase of recommended products to users who are likely to live in a living environment. Therefore, it is possible to recommend the purchase of the product by specifying the user who is more likely to purchase the product and the user who will need to purchase the product in the future.

Each embodiment of the present application has been described in detail with reference to the drawings, but this is an example, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure column of the invention. It is possible to carry out the present invention in other forms applied.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the specific unit can be read as a specific means or a specific circuit.

1 Recommended device 2 User terminal 3 Network 5 Communication unit 6 Control unit 7 Storage unit 11 CPU
12 RAM
13 ROM
14 HDD
15 Communication unit 21 Operating system (OS)
22 Recommendation program corresponding to the first embodiment 23 Sales information 24 User information 31 Specific unit 32 Notification unit 41 Estimating unit 42 Detection unit 51 Recommendation program corresponding to the second embodiment 52 Purchase history information 53 Search information

Claims (12)

Based on the sales information that shows the sales transition of the product, the specific department that identifies the product for which the sales will increase within the specified period, and
It has a notification unit that notifies information of the product before a predetermined period from the time when the sales of the product specified by the specific unit increases.
The notification unit is characterized in that the information of the product is notified to the user who recommends the purchase of the product before a predetermined period from the time when the sales of the product specified by the specific unit increases. Recommended device to do. The recommendation device according to claim 1, wherein the sales information includes at least information indicating the date on which the product was sold and information indicating the number of units sold. It further has an estimation unit that estimates a user with a search history that is the same as or similar to the search history of the purchaser of the product as a user who is expected to purchase the product.
The recommendation device according to claim 1 or 2, wherein the notification unit notifies the user estimated by the estimation unit of information on the product. Based on the information about the living environment of the purchaser at the time when the purchaser purchases the product, the estimation unit purchases the product from a user whose living environment is the same as or similar to the living environment of the purchaser. The recommendation device according to claim 3, wherein the user is estimated as a prospective user. The estimation unit is at least one of a search query entered by the purchaser, a browsing history which is information about the content viewed by the purchaser, and a purchase history which is information about the product purchased by the purchaser. The recommended device according to claim 3 or 4, wherein the information regarding the living environment of the purchaser is estimated based on one. From claim 1, the specific unit specifies the product as a product that is expected to be sold out in the future when the sales of the product increase within a predetermined period from the current date and time. The recommended device according to any one of claims 5. The request from claim 1 is characterized in that the notification unit gives the notification to the effect that the time when the sales of the product increases is near within a predetermined period from the current date and time to the time when the sales of the product increase. Item 6. The recommended device according to any one of items 6. The notification unit notifies the information of the product before a predetermined period from the time when the sales of the product specified by the specific unit increases, so that the product is sold out due to the increase in sales in a timely manner. Any of claims 1 to 7, characterized in that the purchase of the product is recommended to a user who may need the product in the future before the purchase of the product becomes difficult. The recommended device described in item 1. A specific step in which a specific department identifies a product for which sales will increase within a predetermined period based on sales information indicating the sales transition of the product.
The notification unit has a notification step for notifying the information of the product within a predetermined period from the time when the sales of the product specified by the specific unit increase.
In the notification step , the notification unit notifies the user who recommends the purchase of the product of the information of the product within a predetermined period from the time when the sales of the product specified by the specific unit increases. A recommendation method characterized by doing. The estimation unit further includes an estimation step of estimating a user with a search history same as or similar to the search history of the purchaser of the product as a user who is expected to purchase the product.
The recommendation method according to claim 9 , wherein in the notification step , the notification unit notifies the user estimated by the estimation unit of the information of the product. Based on the sales information that shows the sales transition of the product, the specific procedure to identify the product that will increase the sales within the specified period, and the specific procedure.
A computer is made to execute a notification procedure for notifying information on the product within a predetermined period from the time when the sales of the product specified by the specific procedure increase .
The notification procedure is characterized in that the information of the product is notified to the user who recommends the purchase of the product before a predetermined period from the time when the sales of the product specified by the specific procedure increases. Recommendation program to do. Further, the computer is made to perform an estimation procedure for estimating a user with a search history having the same or similar search history as the purchaser of the product as a user who is expected to purchase the product.
The recommendation program according to claim 11 , wherein in the notification procedure, information on the product is notified to the user estimated by the estimation procedure.

Images